异常用电识别特征库构建技术
Construction Technology of Abnormal Electricity Identification Feature Library
DOI: 10.12677/JEE.2023.113015, PDF,    科研立项经费支持
作者: 余武强, 马 筱, 王志敏, 杨宏香, 苏志诚：云南电网有限责任公司丽江供电局，云南 丽江
关键词: 异常用电；特征库；机器学习；Abnormal Electricity； Feature Library； Machine Learning
摘要: 文章旨在介绍构建异常用电识别特征库的方法。首先，对典型用电负荷特征进行设计，包括峰值、谷值、平均值、功率因数等指标，并将其存储到数据库中。接着，对异常用电负荷的特征进行分析，如突变、周期性、持续时间等，并开发相应算法对其进行处理和提取，最终将得到的特征存入异常用电负荷特征库中。在异常用电识别特征库实现方面，利用机器学习技术，对所提取的异常用电负荷特征进行训练，并生成识别模型，以便快速准确地检测和识别异常用电。通过文章，可以更好地了解异常用电的特点和规律，为电力系统的安全运行提供可靠保障。
Abstract: The purpose of this paper is to introduce the method of constructing abnormal electricity identi-fication feature library. Firstly, the typical power load characteristics are designed, including peak value, valley value, average value, power factor and other indicators, and stored in the database. Then, the characteristics of abnormal power load are analyzed, such as mutation, periodicity, duration, etc., and corresponding algorithms are developed to process and extract them. Finally, the obtained features are stored in the abnormal power load feature library. In the realization of the abnormal electricity identification feature library, the machine learning technology is used to train the extracted abnormal electricity load features and generate the recognition model, so as to quickly and accurately detect and identify abnormal electricity. Through this paper, we can better understand the characteristics and laws of abnormal electricity consumption, and provide reliable guarantee for the safe operation of power system.
文章引用：余武强, 马筱, 王志敏, 杨宏香, 苏志诚. 异常用电识别特征库构建技术[J]. 电气工程, 2023, 11(3): 125-136. https://doi.org/10.12677/JEE.2023.113015

参考文献

[1] 孙可, 裴传逊, 翁秉宇. 转型发展形势下城市电网发展协调性评价[J]. 电气工程, 2020, 8(3): 98-108. [Google Scholar] [CrossRef] 
[2] 张少锋. 基于线性判别分析和密度峰值聚类的异常用电模式检测[D]: [硕士学位论文]. 吉林: 东北电力大学, 2022.
[3] 李敏, 王诚意, 蔡嘉辉, 等. 基于专家系统的台区线损异常智能诊断方法及应用[J]. 电力需求侧管理, 2021, 23(5): 81-85.
[4] 王巨灏, 蔡嘉辉, 王琨, 等. 基于WinCC平台的台区线损异常监测系统开发[J]. 电工技术, 2021(8): 163-165.
[5] 肖柳明, 张万, 王言, 等. 安全用电智能监控系统设计[J]. 信息技术与信息化, 2020(12): 216-219.
[6] Oprea, S.V., Bâra, A. and Mircea, M. (2017) Data Acquisition Solutions for Electricity Consumers Connected to Smart Grids. 18th International Carpathian Control Conference (ICCC), Sinaia, 28-31 May 2017, 70-75. [Google Scholar] [CrossRef] 
[7] 祁兵, 刘利亚, 张瑜, 等. 居民负荷特征研究及特征库的建立[J]. 东北电力技术, 2018, 39(6): 1-8.
[8] Jian, L., Ng, S.K.K., Kendall, G., et al. (2010) Load Signature Study—Part II: Disaggregation Framework, Simulation, and Applications. IEEE Transactions on Power Delivery, 25, 561-569.
[9] Bouhouras, A.S., Milioudis, A.N., Andreou, G.T., et al. (2012) Load Signatures Improvement through the Determination of a Spectral Distribution Coefficient for Load Identification. 2012 9th International Conference on the European Energy Market, Florence, 10-12 May 2012, 1-6. [Google Scholar] [CrossRef] 
[10] Martins, J.F., Lopes, R., Lima, C., Romero-Cadaval, E., et al. (2012) A Novel Nonintrusive Load Monitoring System Based on the S-Transform. IEEE International Conference on Optimization of Electrical & Electronic Equipment, Brasov, 24-26 May 2012, 973-978. [Google Scholar] [CrossRef] 
[11] 李波, 李治, 张劲松, 等. 基于需求侧响应的能源服务系统设计[J]. 电气工程, 2021, 9(1): 38-42. [Google Scholar] [CrossRef] 
[12] 陈道远. 基于轻量级J2EE框架的工会综合信息系统的设计与实现[D]: [硕士学位论文]. 广州: 华南理工大学, 2009.
[13] 孙瑶. 轻量级J2EE框架的研究与应用[D]: [硕士学位论文]. 大连: 大连海事大学. 2008.
[14] 柴晓路. 用J2EE架构企业级应用[M]. 北京: UML软件工程组织, 2003: 11-20.
[15] 张加涛, 刘海涛, 李小虎. 面向智能变电站的监控系统分析[J]. 电气工程, 2013, 1(1): 12-17. http://dx.doi.org/10.12677/jee.2013.11003 [Google Scholar] [CrossRef] 
[16] Alur, D., Crupi, J. and Malks, D. (2001) Core J2EE Pattern: Best Practices and Design Strategies. Mechanical Industry Press, Beijing.
[17] 吴建军. 基于J2EE架构的电厂检修管理系统的设计与实现[J]. 热力发电, 2008, 37(11): 101-103.
[18] 谢先明, 刘斌. 基于J2EE架构的生产管理系统及其特性探讨[J]. 华中电力, 2007, 20(1): 35-36+41.
[19] 闵涛, 严小文, 李捷, 等. 基于J2EE架构的新一代电能量计量系统[J]. 电力系统自动化, 2003, 27(22): 85-88.